On Sat, Mar 12, 2016 at 10:30 AM, Matthew Wilcox <willy(a)linux.intel.com> wrote:
On Fri, Mar 11, 2016 at 01:40:20PM -0800, Dan Williams wrote:
> On Fri, Mar 11, 2016 at 1:13 PM, Matthew Wilcox
> <matthew.r.wilcox(a)intel.com> wrote:
> > By moving the flag bits to the bottom, we encourage commonality
> > between SGs with pages and those using pfn_t. We can also then insert
> > a pfn_t into a radix tree, as it uses the same two bits for indirect &
> > exceptional indicators.
> It's not immediately clear to me what we gain with SG entry
> commonality. The down side is that we lose the property that
> pfn_to_pfn_t() is a nop. This was Dave's suggestion so that the
> nominal case did not change the binary layout of a typical pfn.
I understand that motivation!
> Can we just bit swizzle a pfn_t on insertion/retrieval from the radix?
Of course we *can*, but we end up doing more swizzling that way than we
do this way. In the Brave New Future where we're storing pfn_t in the
radix tree, on a page fault we find the pfn_t in the radix tree then
we want to insert it into the page tables. So DAX would first have to
convert the radix tree entry to a pfn_t, then the page table code has to
convert the pfn_t into a pte/pmd/pud (which we currently do by converting
a pfn_t to a pfn, then converting the pfn to a pte/pmd/pud, but I assume
that either the compiler optimises that into a single conversion, or we'll
add pfn_t_pte to each architecture in future if it's actually a problem).
Much easier to look up a pfn_t in the radix tree and pass it directly
If there's any part of the kernel that is doing a *lot* of conversion
between pfn_t and pfn, that surely indicates a place in the kernel where
we need to convert an interface from pfn to pfn_t.
So this is dependent on where pfn_t gets pushed in the future. For
example, if we revive using a pfn_t in a bio then I think the
pfn_to_pfn_t() conversions will be more prevalent than the fs/dax.c